A Prostate Segmentation of TRUS Image using Support Vectors and Snake-like Contour

PARK JAE HEUNG; Yeong-Geon Seo

Journal of The Korea Society of Computer and Information

Abbr : JKSCI
2012, 17(12), pp.101-109
Publisher : The Korean Society Of Computer And Information
Research Area : Computer Science

PARK JAE HEUNG ¹, Yeong-Geon Seo ²

¹경상대학교
²경상대학교

ABSTRACT

In many diagnostic and treatment procedures for prostate disease accurate detection of prostate boundaries in transrectal ultrasound(TRUS) images is required. This is a challenging and difficult task due to weak prostate boundaries, speckle noise and the short range of gray levels. In this paper a method for automatic prostate segmentation inTRUS images using support vectors and snake-like contour is presented. This method involves preprocessing, extracting Gabor feature, training, and prostate segmentation. Gabor filter bank for extracting the texture features has been implemented. A support vector machine(SVM) for training step has been used to get each feature of prostate and nonprostate. The boundary of prostate is extracted by the snake-like contour algorithm. The results showed that this new algorithm extracted the prostate boundary with less than 9.3% relative to boundary provided manually by experts.
KEYWORDS

Support Vector, Snake-like Contour, TRUS, Prostate
REFERENCES (15)

[report] / Cancer Facts and Figures / American Cancer Society

[journal] Mettlin C / 1995 / American society nationalcancer detectionproject / Cancer 75 : 1790~1794

[web] / http://www.cancer.org/Research/CancerFacts Figures/CancerFactsFigures/cancer-facts-figu res-2011 / http://www.cancer.org/Research/CancerFactsFigures/CancerFactsFigures/cancer-facts-figures-2011

[journal] A. Chakraborty / 1996 / Deformable Boundary Finding in MedicalImages by Integrating Gradient and Region Information / IEEE Trans. Med. Imag 15(6) : 859~870

[journal] P. D. Grimm / 1994 / US GuidedTransperinealImplantationofIodine125 andPalladium 103fortheTreatmentofEarly Stage Prostate Cancer / AtlasUrol. Clin. No. Amer 2 : 113~125

[journal] Y.Zhan / Deformable Segmentation of 3-D US Prostate Images Using Statistical Texture Matching Method / Trans. on Med.Imag. 256 : 245~255

[journal] A. Rafiee / 2008 / A Novel Prostate Segmentation Algorithm in TRUS Images / World Academy ofScience,Eng.and Tech 45 : 120~124

[journal] S. D. Pathak / 2009 / Edge-guided Boundary Delineation in ProstateUSImages / IEEE Trans. Med. Imag 19(12) : 1211~1221

[journal] D. Shen / 2003 / Segmentation Prostate Boundaries fromUltrasound Images Using Statistical ShapeModel / IEEETrans. Med. Imag 22(4) : 539~551

[confproc] F. Shao / 2003 / 3-D Prostate Surface Detection from Ultrasound Imagesbasedon LevelSetMethod / in Proc. MICCAI2003 : 389~396

[journal] P. Yan / 2011 / AdaptivelyLearningLocalShapeStatisticsforProstate Segmentation in Ultrasound / IEEETrans. On Bio. Eng 58(3) : 633~641

[confproc] H. Akbari / 2011 / 3D Segmentation of Prostate US Images Using WaveletTransform / Proc. ofSPIE

[confproc] B. E. Boser / 1992 / A Training Algorithm for Optimal Margin Classifiers / In D.Haussler,5th AnnualACM WorkshoponCOLT : 144~152

[book] J. Suri / 2007 / DeformableModels2 / Springer : 75~94

[journal] A. Ghanei / 2001 / A 3D Deformable ModelforSegmentation ofHumanProstatefrom UltrasoundImage / Med.Phys. 28 : 2147~2153
KCI Citation (2)

KJC Korea
Journal Central

Statistics

Tools